Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Common-sense Reasoning on ARC easy

69.87ARC (easy) Accuracy

Mamba2

23.995635.905347.81559.7247Jun 26, 2023Dec 10, 2023May 26, 2024Nov 9, 2024Apr 26, 2025Oct 10, 2025Mar 27, 2026
Updated 10d ago

Evaluation Results

MethodLinks
2026.03
69.87--
2026.03
68.48--
2026.02
67.97--
2026.03
67.63--
2025.09
64.3--
2025.09
64--
2026.03
63.68--
2026.03
63--
2026.03
62.9--
2026.03
62.9--
2026.03
62.7--
2026.03
62.3--
2024.09
61.9--
2024.09
60.8--
2024.09
60.7--
2024.02
59.85--
2024.09
59.8--
2024.09
59.6--
2024.09
59.2--
2024.02
58.92--
2024.02
58.75--
2024.09
58.1--
2024.09
58.1--
2026.02
58.04--
2024.09
57.4--
2024.09
57.1--
2024.09
55.4--
2025.09
54.5--
2025.12
54.4--
2024.09
54.1--
2025.09
53.9--
2024.02
53.66--
2024.02
52.65--
2024.02
52.61--
2024.02
52.57--
2024.02
52.53--
2025.12
52.5--
2024.02
52.15--
2024.02
52.06--
2024.02
51.18--
2025.11
50.88--
2025.11
50.35--
2023.06
49.581.6160.56
2024.02
49.58--
2024.02
49.54--
2024.02
49.49--
2023.06
49.361.759.61
2023.06
49.221.6260.44
2023.06
49.091.7259.79
2023.06
49.041.6460.02
2023.06
48.811.7559.41
2023.06
47.991.8658.19
2026.03
45.29--
2025.09
45.2--
2026.03
45.03--
2024.02
44.7--
2024.02
44.49--
2026.03
44.49--
2026.03
44.11--
2024.02
43.06--
2025.12
42.5--
2026.03
42.09--
2026.03
42.05--
2025.12
41.8--
2025.12
41.5--
2024.02
40.99--
2025.12
40.4--
2024.02
34.22--
2024.02
32.11--
2024.02
27.19--
2024.02
26.22--
2024.02
25.76--
2026.01
--79.7
2026.01
--81.6